Model: GELU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1291 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 8.2337. Min Range: -8.2337

Max Act: 8.2337. Min Act: -0.1700

Data Index: 479475 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 8.2337. Min Range: -8.2337

Max Act: 8.1712. Min Act: -0.1700

Data Index: 739275 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 8.2337. Min Range: -8.2337

Max Act: 8.1087. Min Act: -0.1700

Data Index: 1143994 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 8.2337. Min Range: -8.2337

Max Act: 7.9837. Min Act: -0.1700

Data Index: 84355 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 8.2337. Min Range: -8.2337

Max Act: 7.8587. Min Act: -0.1700

Data Index: 632157 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 8.2337. Min Range: -8.2337

Max Act: 7.8587. Min Act: -0.1700

Data Index: 952051 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 8.2337. Min Range: -8.2337

Max Act: 7.8274. Min Act: -0.1700

Data Index: 290040 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 8.2337. Min Range: -8.2337

Max Act: 7.8587. Min Act: -0.1700

Data Index: 1233725 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 8.2337. Min Range: -8.2337

Max Act: 7.7962. Min Act: -0.1700

Data Index: 1321445 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 8.2337. Min Range: -8.2337

Max Act: 7.7962. Min Act: -0.1700

Data Index: 504864 (C4 (Web Text))

Max Activating Token Index: 448

Text #10

Max Range: 8.2337. Min Range: -8.2337

Max Act: 7.7649. Min Act: -0.1700

Data Index: 812960 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 8.2337. Min Range: -8.2337

Max Act: 7.6399. Min Act: -0.1700

Data Index: 325880 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 8.2337. Min Range: -8.2337

Max Act: 7.5462. Min Act: -0.1700

Data Index: 885015 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 8.2337. Min Range: -8.2337

Max Act: 7.7024. Min Act: -0.1700

Data Index: 917456 (C4 (Web Text))

Max Activating Token Index: 504

Text #14

Max Range: 8.2337. Min Range: -8.2337

Max Act: 7.6087. Min Act: -0.1700

Data Index: 800815 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 8.2337. Min Range: -8.2337

Max Act: 7.6712. Min Act: -0.1700

Data Index: 208467 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 8.2337. Min Range: -8.2337

Max Act: 7.6087. Min Act: -0.1700

Data Index: 119607 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 8.2337. Min Range: -8.2337

Max Act: 7.6087. Min Act: -0.1700

Data Index: 757995 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 8.2337. Min Range: -8.2337

Max Act: 7.5149. Min Act: -0.1700

Data Index: 1294869 (C4 (Web Text))

Max Activating Token Index: 553

Text #19

Max Range: 8.2337. Min Range: -8.2337

Max Act: 7.4837. Min Act: -0.1700

Data Index: 811775 (C4 (Web Text))

Max Activating Token Index: 1001